Digital Twin of BalancerV2

A synthetic data generator for text recognition

Pusher Client implemented in Python3

A simple baseline for one-shot multi-object tracking

Joint Detection and Embedding for fast multi-object tracking

Open standard for machine learning interoperability

Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.

tensorrt5 , centernet , centerface, deform conv, int8

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

A PyTorch Implementation of Single Shot MultiBox Detector

E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%

Adversarially Learned One-Class Classifier for Novelty Detection

Open Source Computer Vision Library

The rep for the Crowd Counting paper accepted by CVPR 2018

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

Learning to share: simultaneous parameter tying and sparsification in deep learning

Crowd Counting Via Scale-adaptive Convolutional Neural Network

Caffe Implementation of Google's MobileNets (v1 and v2)

Computation using data flow graphs for scalable machine learning

Caffe for Sparse and Low-rank Deep Neural Networks

Caffe Protofiles for MSRA ResNet: train prototxt

Focal loss for Dense Object Detection

Datasets, Transforms and Models specific to Computer Vision

ImageNet pre-trained models with batch normalization for the Caffe framework

Caffe fork that supports SPP_net or faster R-CNN

A Caffe Re-Implementation of SENet

Deep Residual Learning for Image Recognition

Caffe models (imagenet pretrain) and prototxt generator scripts for inception_v3 \ inception_v4 \ inception_resnet \ fractalnet \ resnext